Identifies underpenetrated metro areas for specialty EHR adoption using CMS NPPES provider density, Census demographics, and Medicare utilization signals.
●Pipeline output: 90 metro × specialty scores from spectrumiq_pipeline.py · 18 metros for Dermatology
Sort by:
#Metro AreaProvidersPer 100KScoreOpportunityTier
1Tampa-St. Petersburg, FL2186.865
Moderate
2Las Vegas, NV1677.464
Moderate
3Nashville, TN1447.261
Moderate
4Dallas-Fort Worth, TX5156.760
Moderate
5Charlotte, NC2509.455
Moderate
6Miami-Fort Lauderdale, FL65710.754
Moderate
7Jacksonville, FL1559.753
Moderate
8Orlando, FL30211.352
Moderate
9Phoenix, AZ76215.450
Moderate
10Austin, TX37716.550
Moderate
11Houston, TX73110.349
Moderate
12Denver, CO30110.248
Moderate
13Raleigh-Durham, NC23816.847
Moderate
14Atlanta, GA89214.542
Low Priority
15Salt Lake City, UT1861542
Low Priority
16San Antonio, TX40815.941
Low Priority
17Columbus, OH25211.841
Low Priority
18Indianapolis, IN3161537
Low Priority
Methodology & Data Pipeline
Data produced by spectrumiq_pipeline.py — a Python ETL pipeline that processes CMS NPPES provider data filtered by specialty taxonomy codes, joins to Census metro populations via ZIP-code mapping, and computes weighted composite scores. Weights: Provider Gap (35%), Population Growth (25%), Medicare Density (20%), Income Index (20%). Pipeline output validated with automated data quality checks (see test_pipeline.py). Full source in data/pipeline/.